{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:15:52Z","timestamp":1783610152933,"version":"3.55.0"},"reference-count":183,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2128448"],"award-info":[{"award-number":["CNS-2128448"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["2007714"],"award-info":[{"award-number":["2007714"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["2139304"],"award-info":[{"award-number":["2139304"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["2146838"],"award-info":[{"award-number":["2146838"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010198","name":"U.S. Army Research Office under MURI","doi-asserted-by":"publisher","award":["AG285"],"award-info":[{"award-number":["AG285"]}],"id":[{"id":"10.13039\/100010198","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"U.S. Army Research Laboratory Cooperative","doi-asserted-by":"publisher","award":["W911NF-17-2-0196"],"award-info":[{"award-number":["W911NF-17-2-0196"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62203373"],"award-info":[{"award-number":["62203373"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1109\/jsac.2023.3242710","type":"journal-article","created":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T18:45:39Z","timestamp":1675709139000},"page":"851-873","source":"Crossref","is-referenced-by-count":115,"title":["Communication-Efficient Distributed Learning: An Overview"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0190-4362","authenticated-orcid":false,"given":"Xuanyu","family":"Cao","sequence":"first","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4406-7875","authenticated-orcid":false,"given":"Tamer","family":"Ba\u015far","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Illinois Urbana–Champaign, Urbana–Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7313-9861","authenticated-orcid":false,"given":"Suhas","family":"Diggavi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of California, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4358-5304","authenticated-orcid":false,"given":"Yonina C.","family":"Eldar","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Weizmann Institute of Science, Rehovot, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2519-6401","authenticated-orcid":false,"given":"Khaled B.","family":"Letaief","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2062-131X","authenticated-orcid":false,"given":"H. Vincent","family":"Poor","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3840-1753","authenticated-orcid":false,"given":"Junshan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of California, Davis, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","first-page":"1","article-title":"Cooperative SGD: A unified framework for the design and analysis of local-update SGD algorithms","volume":"22","author":"wang","year":"2021","journal-title":"J Mach Learn Res"},{"key":"ref56","article-title":"Deep learning with elastic averaging SGD","author":"zhang","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118344"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-018-1355-4"},{"key":"ref53","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume":"33","author":"wang","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref52","first-page":"212","article-title":"Adaptive communication strategies to achieve the best error-runtime trade-off in local-update SGD","author":"wang","year":"2019","journal-title":"Conf Mach Learn Syst"},{"key":"ref55","first-page":"10334","article-title":"Is local SGD better than minibatch SGD?","author":"woodworth","year":"2020","journal-title":"Int Conf Mach Learn"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118435"},{"key":"ref54","article-title":"SlowMo: Improving communication-efficient distributed SGD with slow momentum","author":"wang","year":"2020","journal-title":"Int Conf Learn Represent"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3031503"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3042530"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118352"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3099505"},{"key":"ref51","first-page":"11082","article-title":"Local SGD with periodic averaging: Tighter analysis and adaptive synchronization","author":"haddadpour","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118353"},{"key":"ref50","article-title":"Don’t use large mini-batches, use local SGD","author":"lin","year":"2020","journal-title":"Int Conf Learn Represent"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054634"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126052"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.3390\/e23111413"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3025446"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118351"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2750110"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2412918"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref47","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Int Conf Arti Intel Stat"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2989266"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2018.2806841"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2333560"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118431"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2686368"},{"key":"ref49","article-title":"Local SGD converges fast and communicates little","author":"stich","year":"2019","journal-title":"Int Conf Learn Represent"},{"key":"ref8","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"lin","year":"2018","journal-title":"Int Conf Learn Represent"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2940820"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-354"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2967772"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3024629"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2617829"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2304432"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2005.843546"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3014095"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3031073"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2295055"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.2994639"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118401"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2436358"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2666776"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2012.191"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2548989"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/14096668X"},{"key":"ref148","first-page":"1","article-title":"Error compensated distributed SGD can be accelerated","author":"qian","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2364096"},{"key":"ref149","first-page":"1","article-title":"ErrorCompensatedX: Error compensation for variance reduced algorithms","author":"tang","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2020.3024321"},{"key":"ref146","first-page":"1","article-title":"Qsparse-local-SGD: Distributed SGD with quantization, sparsification, and local computations","author":"basu","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2937496"},{"key":"ref147","first-page":"1","article-title":"Linearly converging error compensated SGD","author":"gorbunov","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2015.2505149"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2449255"},{"key":"ref155","first-page":"8253","article-title":"FetchSGD: Communication-efficient federated learning with sketching","author":"rothchild","year":"2020","journal-title":"Int Conf Mach Learn"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029257"},{"key":"ref153","article-title":"Federated learning: Strategies for improving communication efficiency","author":"kone?n?","year":"2016","journal-title":"NIPS Workshop on Private Multi-Party Machine Learning PMPML '16"},{"key":"ref154","first-page":"1","article-title":"PowerSGD: Practical low-rank gradient compression for distributed optimization","volume":"32","author":"vogels","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3048229"},{"key":"ref152","article-title":"Decentralized multi-task stochastic optimization with compressed communications","author":"singh","year":"2021","journal-title":"arXiv 2112 12373"},{"key":"ref150","first-page":"6155","article-title":"DoubleSqueeze: Parallel stochastic gradient descent with double-pass error-compensated compression","author":"tang","year":"2019","journal-title":"Int Conf Mach Learn"},{"key":"ref24","first-page":"21394","article-title":"Personalized federated learning with Moreau envelopes","volume":"33","author":"dinh","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"3557","article-title":"Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","volume":"33","author":"fallah","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref26","first-page":"2304","article-title":"Lower bounds and optimal algorithms for personalized federated learning","volume":"33","author":"hanzely","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref25","article-title":"QuPeD: Quantized personalization via distillation with applications to federated learning","volume":"34","author":"ozkara","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2538028"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3090323"},{"key":"ref22","first-page":"9537","article-title":"Probabilistic model-agnostic meta-learning","author":"finn","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2961673"},{"key":"ref21","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Int Conf Mach Learn"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946245"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/16M1084316"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2010.2041686"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2972824"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126078"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118436"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.3035770"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126060"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3037554"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737464"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488818"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118402"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3125282"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126076"},{"key":"ref15","author":"boyd","year":"2011","journal-title":"Distributed optimization and statistical learning via the alternating direction method of multipliers"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2974748"},{"key":"ref14","author":"bertsekas","year":"1989","journal-title":"Parallel and Distributed Computation Numerical Methods"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2981904"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118428"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00220"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3031018"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118396"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2600597"},{"key":"ref124","first-page":"979","article-title":"99% of worker-master communication in distributed optimization is not needed","author":"mishchenko","year":"2020","journal-title":"Conf Uncertainty Artif Intell"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036944"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126081"},{"key":"ref125","first-page":"1","article-title":"Rethinking gradient sparsification as total error minimization","volume":"34","author":"sahu","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1561\/2400000013"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1561\/2200000018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098136"},{"key":"ref18","first-page":"928","article-title":"Online convex programming and generalized infinitesimal gradient ascent","author":"zinkevich","year":"2003","journal-title":"20th Int Conf Machine Learning"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029541"},{"key":"ref133","first-page":"1306","article-title":"Gradient sparsification for communication-efficient distributed optimization","author":"wangni","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2504341"},{"key":"ref134","first-page":"2530","article-title":"A linear speedup analysis of distributed deep learning with sparse and quantized communication","author":"jiang","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2932876"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3038407"},{"key":"ref94","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume":"30","author":"alistarh","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref132","first-page":"9872","article-title":"ATOMO: Communication-efficient learning via atomic sparsification","author":"wang","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00026"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2012.06.004"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3046971"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2008.4738860"},{"key":"ref139","first-page":"7663","article-title":"Communication compression for decentralized training","author":"tang","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref86","article-title":"The min-max complexity of distributed stochastic convex optimization with intermittent communication","author":"woodworth","year":"2021","journal-title":"34th Annu Conf Learn Theory"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356222"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975994.106"},{"key":"ref138","first-page":"3478","article-title":"Decentralized stochastic optimization and gossip algorithms with compressed communication","author":"koloskova","year":"2019","journal-title":"Int Conf Mach Learn"},{"key":"ref88","first-page":"1399","article-title":"RATQ: A universal fixed-length quantizer for stochastic optimization","author":"mayekar","year":"2020","journal-title":"Int Conf Arti Intel Stat"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT44484.2020.9174216"},{"key":"ref87","article-title":"Information-theoretic lower bounds on the Oracle complexity of convex optimization","volume":"22","author":"agarwal","year":"2009","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref136","article-title":"eSGD: Communication efficient distributed deep learning on the edge","author":"tao","year":"2018","journal-title":"USENIX Workshop on Hot Topics in Edge Computing"},{"key":"ref82","first-page":"2545","article-title":"Trading redundancy for communication: Speeding up distributed SGD for non-convex optimization","author":"haddadpour","year":"2019","journal-title":"Int Conf Mach Learn"},{"key":"ref144","first-page":"5325","article-title":"Error compensated quantized SGD and its applications to large-scale distributed optimization","author":"wu","year":"2018","journal-title":"Int Conf Mach Learn"},{"key":"ref81","first-page":"7174","article-title":"On the computation and communication complexity of parallel SGD with dynamic batch sizes for stochastic non-convex optimization","author":"yu","year":"2019","journal-title":"Int Conf Mach Learn"},{"key":"ref145","first-page":"3252","article-title":"Error feedback fixes signSGD and other gradient compression schemes","author":"karimireddy","year":"2019","journal-title":"Int Conf Mach Learn"},{"key":"ref84","first-page":"1756","article-title":"Communication complexity of distributed convex learning and optimization","author":"arjevani","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref142","article-title":"Decentralized deep learning with arbitrary communication compression","author":"koloskova","year":"2020","journal-title":"Int Conf Learn Represent"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/0885-064X(87)90013-6"},{"key":"ref143","first-page":"4452","article-title":"Sparsified SGD with memory","author":"stich","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3145576"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3103920"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3078100"},{"key":"ref79","first-page":"3370","article-title":"Communication-efficient distributed learning via lazily aggregated quantized gradients","author":"sun","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref108","first-page":"3696","article-title":"Quantized Frank-Wolfe: Communication-efficient distributed optimization","author":"zhang","year":"2020","journal-title":"Int Conf Arti Intel Stat"},{"key":"ref78","article-title":"LAG: Lazily aggregated gradient for communication-efficient distributed learning","author":"chen","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2997394"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2983166"},{"key":"ref107","first-page":"4438","article-title":"Double quantization for communication-efficient distributed optimization","volume":"32","author":"yu","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3044843"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2014.2357513"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2907258"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2681119"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2694323"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2989281"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2016.2585305"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2018.8645345"},{"key":"ref2","first-page":"2503","article-title":"Trading regret for efficiency: Online convex optimization with long term constraints","volume":"13","author":"mahdavi","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3122927"},{"key":"ref111","first-page":"1508","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","author":"wen","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref70","first-page":"49","article-title":"Event-triggered distributed optimization in sensor networks","author":"wan","year":"2009","journal-title":"Inf Process Sensor Netw"},{"key":"ref112","first-page":"560","article-title":"SignSGD: Compressed optimisation for non-convex problems","author":"bernstein","year":"2018","journal-title":"Int Conf Mach Learn"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2873517"},{"key":"ref72","article-title":"Gradient-push algorithm for distributed optimization with event-triggered communications","author":"kim","year":"2021","journal-title":"arXiv 2111 06315"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3105359"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619311"},{"key":"ref119","first-page":"2021","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization","author":"reisizadeh","year":"2020","journal-title":"Int Conf Arti Intel Stat"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2867175"},{"key":"ref117","first-page":"1","article-title":"Communication-efficient federated learning","volume":"118","author":"chen","year":"2021","journal-title":"Nat Acad Sci USA"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.11.015"},{"key":"ref118","article-title":"Stochastic distributed learning with gradient quantization and variance reduction","author":"horv\u00e1th","year":"2019","journal-title":"arXiv 1904 05115"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2010.2049518"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109676"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2916985"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118415"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6206"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3039309"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2800760"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2884998"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9148862"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"key":"ref123","first-page":"5973","article-title":"The convergence of sparsified gradient methods","author":"alistarh","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2953131"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3041388"},{"key":"ref61","first-page":"3068","article-title":"Communication-efficient distributed dual coordinate ascent","author":"jaggi","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref121","first-page":"7575","article-title":"CpSGD: Communication-efficient and differentially-private distributed SGD","author":"agarwal","year":"2018","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/49\/10075675\/10038471-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/10075675\/10038471.pdf?arnumber=10038471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T19:18:42Z","timestamp":1681154322000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10038471\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":183,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2023.3242710","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"value":"0733-8716","type":"print"},{"value":"1558-0008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4]]}}}